CSC-Unet: A Novel Convolutional Sparse Coding Strategy based Neural Network for Semantic Segmentation

It is still a challenging task to perform the semantic segmentation with high accuracy due to the complexity of real picture scenes. Many semantic segmentation methods based on traditional deep learning insufficiently captured the semantic and appearance information of images, which put limit on the...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2024-01, Vol.12, p.1-1
Main Authors: Tang, Haitong, He, Shuang, Yang, Mengduo, Lu, Xia, Yu, Qin, Liu, Kaiyue, Yan, Hongjie, Wang, Nizhuan
Format: Article
Language:English
Subjects:
Coding
Convolution
Convolution operation
Convolutional codes
Convolutional neural networks
Convolutional sparse coding (CSC)
Datasets
Deep learning
Encoding
Image coding
Mathematical models
Multilayers
Neural networks
Semantic segmentation
Semantics
U-Net
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:It is still a challenging task to perform the semantic segmentation with high accuracy due to the complexity of real picture scenes. Many semantic segmentation methods based on traditional deep learning insufficiently captured the semantic and appearance information of images, which put limit on their generality and robustness for various application scenes. Thus, in this paper, we proposed a novel strategy that reformulated the popularly used convolution operation to multi-layer convolutional sparse coding block in semantic segmentation method to ease the aforementioned deficiency. To prove the effectiveness of our idea, we chose the widely used U-Net model for the demonstration purpose, and we designed CSC-Unet model series based on U-Net. Through extensive analysis and experiments, we provided credible evidence showing that the multi-layer convolutional sparse coding block enables semantic segmentation model to converge faster, extract finer semantic and appearance information of images, and improve the ability to recover spatial detail information. The best CSC-Unet model significantly outperforms the results of the original U-Net on three public datasets with different scenarios, i.e., 87.14% vs. 84.71% on DeepCrack dataset, 68.91% vs. 67.09% on Nuclei dataset, and 53.68% vs. 48.82% on CamVid dataset, respectively. In addition, the proposed strategy could be possibly used to significantly improve segmentation performance of any semantic segmentation model that involves convolution operations and the corresponding code is available at https://github.com/NZWANG/CSC-Unet.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2024.3373619